+ HEALTH Background Laryngeal cancer is a significant global health issue with high mortality, and early diagnosis is…+ LABOR This scoping review consolidates existing technology-enabled interventions for preventing and responding to a…+ HEALTH Background Assessment of pulmonary vascularity on chest radiographs (CXRs) in congenital heart disease (CHD)…− HEALTH Most artificial intelligence (AI) models used in radiology are black boxes-they produce predictions without e…− HEALTH Background The anion gap is primarily utilized as an indicator for evaluating acid-base imbalances in critica…+ HEALTH Introduction Combat Medical Technicians (CMTs) are central to military primary care but have limited opportun…+ HEALTH Objective This study aimed to evaluate the structural characteristics of mandibular alveolar bone in patients…+ MEDIA & ARTS Look, we all want Brooke Shields to be in gainful employment. We all want her to have a fabulous third act to…
TruaceTracing the truth around AISaturday, August 22, 2026
Subscribe
Health·P Space·Evidence-backed problem·Published 2026-08-22

Explainable artificial intelligence in medical imaging: how to interpret, evaluate, and use artificial intelligence explanations

Abstract: Most artificial intelligence (AI) models used in radiology are black boxes-they produce predictions without explaining the basis of their outputs, raising concerns about clinical safety, accountability, and trust. To address this, a growing body of methods has been developed to help clinicians understand and evaluate AI predictions. This field, known as explainable AI (XAI), aims to help clinicians interrogate, interpret, and critically evaluate AI predictions by identifying factors associated with model outputs…

TRV-2026-0847Peer-reviewedPermanent record — cite & verify
Explainable artificial intelligence in medical imaging: how to interpret, evaluate, and use artificial intelligence explanations

Bust del Doctor Valentí Carulla (Hospital Clínic) by Pere prlpz. CC BY-SA 3.0 · https://creativecommons.org/licenses/by-sa/3.0

The quick read

Most artificial intelligence (AI) models used in radiology are black boxes-they produce predictions without explaining the basis of their outputs, raising concerns about clinical safety, accountability, and trust. To address this, a growing body of methods has been developed to help clinicians understand and evaluate AI predictions.

This field, known as explainable AI (XAI), aims to help clinicians interrogate, interpret, and critically evaluate AI predictions by identifying factors associated with model outputs. We aim to make XAI easier for healthcare professionals to understand, as effective oversight of AI tools has become a core competency for the modern radiologist.

Main points
  • To address this, a growing body of methods has been developed to help clinicians understand and evaluate AI predictions.
  • This field, known as explainable AI (XAI), aims to help clinicians interrogate, interpret, and critically evaluate AI predictions by identifying factors associated with model outputs.
  • In this educational and practical review, we provide an accessible overview of XAI tailored for practicing radiologists and physicians.
Problem

Most artificial intelligence (AI) models used in radiology are black boxes-they produce predictions without explaining the basis of their outputs, raising concerns about clinical safety, accountability, and trust.

The rundown

This field, known as explainable AI (XAI), aims to help clinicians interrogate, interpret, and critically evaluate AI predictions by identifying factors associated with model outputs. In this educational and practical review, we provide an accessible overview of XAI tailored for practicing radiologists and physicians.

Sources

Reader signal

How should this claim be treated?

The debate